OV - exec - Loop 348

	Loop Id: 348	Module: exec	Source: BsplineFunctor.h:236-241	Coverage: 2.11%

0x420398 LDR	D6, [X16]    [2]

0x42039c FCMPE	D6, D31

0x4203a0 B.GE	4203b4

0x4203a4 CMP	W23, W13

0x4203a8 B.EQ	4203b4

0x4203ac STR	D6, [X6, X4,UXTW #3]    [1]

0x4203b0 ADD	W4, W4, #1

0x4203b4 LDR	D7, [X16, #8]    [2]

0x4203b8 ADD	W30, W13, #1

0x4203bc ADD	X0, X16, #8

0x4203c0 FCMPE	D7, D31

0x4203c4 B.GE	4203d8

0x4203c8 CMP	W23, W30

0x4203cc B.EQ	4203d8

0x4203d0 STR	D7, [X6, X4,UXTW #3]    [1]

0x4203d4 ADD	W4, W4, #1

0x4203d8 LDR	D8, [X0, #8]    [3]

0x4203dc ADD	W1, W30, #1

0x4203e0 FCMPE	D8, D31

0x4203e4 B.GE	4203f8

0x4203e8 CMP	W23, W1

0x4203ec B.EQ	4203f8

0x4203f0 STR	D8, [X6, X4,UXTW #3]    [1]

0x4203f4 ADD	W4, W4, #1

0x4203f8 LDR	D9, [X0, #16]    [3]

0x4203fc ADD	W2, W30, #2

0x420400 FCMPE	D9, D31

0x420404 B.GE	420418

0x420408 CMP	W23, W2

0x42040c B.EQ	420418

0x420410 STR	D9, [X6, X4,UXTW #3]    [1]

0x420414 ADD	W4, W4, #1

0x420418 LDR	D10, [X0, #24]    [3]

0x42041c ADD	W28, W30, #3

0x420420 FCMPE	D10, D31

0x420424 B.GE	420438

0x420428 CMP	W23, W28

0x42042c B.EQ	420438

0x420430 STR	D10, [X6, X4,UXTW #3]    [1]

0x420434 ADD	W4, W4, #1

0x420438 LDR	D11, [X0, #32]    [3]

0x42043c ADD	W3, W30, #4

0x420440 FCMPE	D11, D31

0x420444 B.GE	420458

0x420448 CMP	W23, W3

0x42044c B.EQ	420458

0x420450 STR	D11, [X6, X4,UXTW #3]    [1]

0x420454 ADD	W4, W4, #1

0x420458 LDR	D12, [X0, #40]    [3]

0x42045c ADD	W27, W30, #5

0x420460 FCMPE	D12, D31

0x420464 B.GE	420478

0x420468 CMP	W23, W27

0x42046c B.EQ	420478

0x420470 STR	D12, [X6, X4,UXTW #3]    [1]

0x420474 ADD	W4, W4, #1

0x420478 LDR	D13, [X0, #48]    [3]

0x42047c ADD	W12, W30, #6

0x420480 FCMPE	D13, D31

0x420484 B.GE	420498

0x420488 CMP	W23, W12

0x42048c B.EQ	420498

0x420490 STR	D13, [X6, X4,UXTW #3]    [1]

0x420494 ADD	W4, W4, #1

0x420498 ADD	W13, W30, #7

0x42049c ADD	X16, X0, #56

0x4204a0 CMP	W5, W13

0x4204a4 B.NE	420398

/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h: 236 - 241

--------------------------------------------------------------------------------

236:   for (int jat = 0; jat < iLimit; jat++)

237:   {

238:     real_type r = distArray[jat];

239:     // pick the distances smaller than the cutoff and avoid the reference atom

240:     if (r < cutoff_radius && iStart + jat != iat)

241:       distArrayCompressed[iCount++] = distArray[jat];

Coverage (%)	Name	Source Location	Module
►99.01+	qmcplusplus::WaveFunction::eva[...]	stl_vector.h:992	exec
○	main._omp_fn.1	NonLocalPP.hpp:126	exec
○	gomp_thread_start	team.c:130	libgomp.so.1.0.0
○	start_thread		libc.so.6
○	thread_start		libc.so.6

min	med	avg	max

Percentile Index	10	20	30	40	50	60	70	80	90	100
Value

min	med	avg	max

Percentile Index	10	20	30	40	50	60	70	80	90	100
Value

Path /

Metric	Value
CQA speedup if no scalar integer	1.59
CQA speedup if FP arith vectorized	1.00
CQA speedup if fully vectorized	2.13
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.06
Bottlenecks	micro-operation queue, P0, P1,
Function	miniqmcreference::TwoBodyJastrowRef >::evaluateRatios(qmcplusplus::VirtualParticleSet&, std::vector >&)
Source	BsplineFunctor.h:236-241
Source loop unroll info	not unrolled or unrolled with no peel/tail loop
Source loop unroll confidence level	max
Unroll/vectorization loop type	NA
Unroll factor	NA
CQA cycles	8.50
CQA cycles if no scalar integer	5.33
CQA cycles if FP arith vectorized	8.50
CQA cycles if fully vectorized	4.00
Front-end cycles	8.50
P0 cycles	8.50
P1 cycles	8.50
P2 cycles	4.58
P3 cycles	4.58
P4 cycles	4.50
P5 cycles	4.50
P6 cycles	4.42
P7 cycles	4.42
P8 cycles	8.00
P9 cycles	8.00
P10 cycles	0.00
P11 cycles	0.00
P12 cycles	5.33
P13 cycles	5.33
P14 cycles	5.33
P15 cycles	0.00
P16 cycles	0.00
DIV/SQRT cycles	0.00
Inter-iter dependencies cycles	NA
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	68.00
Nb uops	68.00
Nb loads	NA
Nb stores	8.00
Nb stack references	0.00
FLOP/cycle	0.00
Nb FLOP add-sub	0.00
Nb FLOP mul	0.00
Nb FLOP fma	0.00
Nb FLOP div	0.00
Nb FLOP rcp	0.00
Nb FLOP sqrt	0.00
Nb FLOP rsqrt	0.00
Bytes/cycle	15.06
Bytes prefetched	0.00
Bytes loaded	64.00
Bytes stored	64.00
Stride 0	NA
Stride 1	NA
Stride n	NA
Stride unknown	NA
Stride indirect	NA
Vectorization ratio all	0.00
Vectorization ratio load	0.00
Vectorization ratio store	0.00
Vectorization ratio mul	NA
Vectorization ratio add_sub	0.00
Vectorization ratio fma	NA
Vectorization ratio div_sqrt	NA
Vectorization ratio other	0.00
Vector-efficiency ratio all	40.38
Vector-efficiency ratio load	50.00
Vector-efficiency ratio store	50.00
Vector-efficiency ratio mul	NA
Vector-efficiency ratio add_sub	25.00
Vector-efficiency ratio fma	NA
Vector-efficiency ratio div_sqrt	NA
Vector-efficiency ratio other	37.50

Metric	Value
CQA speedup if no scalar integer	1.59
CQA speedup if FP arith vectorized	1.00
CQA speedup if fully vectorized	2.13
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.06
Bottlenecks	micro-operation queue, P0, P1,
Function	miniqmcreference::TwoBodyJastrowRef >::evaluateRatios(qmcplusplus::VirtualParticleSet&, std::vector >&)
Source	BsplineFunctor.h:236-241
Source loop unroll info	not unrolled or unrolled with no peel/tail loop
Source loop unroll confidence level	max
Unroll/vectorization loop type	NA
Unroll factor	NA
CQA cycles	8.50
CQA cycles if no scalar integer	5.33
CQA cycles if FP arith vectorized	8.50
CQA cycles if fully vectorized	4.00
Front-end cycles	8.50
P0 cycles	8.50
P1 cycles	8.50
P2 cycles	4.58
P3 cycles	4.58
P4 cycles	4.50
P5 cycles	4.50
P6 cycles	4.42
P7 cycles	4.42
P8 cycles	8.00
P9 cycles	8.00
P10 cycles	0.00
P11 cycles	0.00
P12 cycles	5.33
P13 cycles	5.33
P14 cycles	5.33
P15 cycles	0.00
P16 cycles	0.00
DIV/SQRT cycles	0.00
Inter-iter dependencies cycles	NA
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	68.00
Nb uops	68.00
Nb loads	NA
Nb stores	8.00
Nb stack references	0.00
FLOP/cycle	0.00
Nb FLOP add-sub	0.00
Nb FLOP mul	0.00
Nb FLOP fma	0.00
Nb FLOP div	0.00
Nb FLOP rcp	0.00
Nb FLOP sqrt	0.00
Nb FLOP rsqrt	0.00
Bytes/cycle	15.06
Bytes prefetched	0.00
Bytes loaded	64.00
Bytes stored	64.00
Stride 0	NA
Stride 1	NA
Stride n	NA
Stride unknown	NA
Stride indirect	NA
Vectorization ratio all	0.00
Vectorization ratio load	0.00
Vectorization ratio store	0.00
Vectorization ratio mul	NA
Vectorization ratio add_sub	0.00
Vectorization ratio fma	NA
Vectorization ratio div_sqrt	NA
Vectorization ratio other	0.00
Vector-efficiency ratio all	40.38
Vector-efficiency ratio load	50.00
Vector-efficiency ratio store	50.00
Vector-efficiency ratio mul	NA
Vector-efficiency ratio add_sub	25.00
Vector-efficiency ratio fma	NA
Vector-efficiency ratio div_sqrt	NA
Vector-efficiency ratio other	37.50

Path /

Average path: Display a virtual path defined by average values of all real paths

Function	miniqmcreference::TwoBodyJastrowRef >::evaluateRatios(qmcplusplus::VirtualParticleSet&, std::vector >&)
Source file and lines	BsplineFunctor.h:236-241
Module	exec

The loop is defined in /home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:236-241.

The related source loop is not unrolled or unrolled with no peel/tail loop.
Warnings:

Ignoring paths for analysis
Too many paths. If you really need to analyze all of the 6561 paths individually, rerun with max-paths=6561
RecMII not computed since number of paths is unknown or > max_paths
Streams not analyzed since number of paths is unknown or > max_paths

Try to simplify control and/or increase the maximum number of paths per function/loop through the 'max-paths-nb' option.

This loop has 6561 execution paths.

The presence of multiple execution paths is typically the main/first bottleneck.
Try to simplify control inside loop: ideally, try to remove all conditional expressions, for example by (if applicable):

hoisting them (moving them outside the loop)
turning them into conditional moves, MIN or MAX

Ex: if (x<0) x=0 => x = (x<0 ? 0 : x) (or MAX(0,x) after defining the corresponding macro)

gain
potential
hint
expert

Code clean check

Detected a slowdown caused by scalar integer instructions (typically used for address computation). By removing them, you can lower the cost of an iteration from 8.50 to 5.33 cycles (1.59x speedup).

Workaround

Try to reorganize arrays of structures to structures of arrays
Consider to permute loops (see vectorization gain report)

Vectorization

Your loop is not vectorized. Only 40% of vector register length is used (average across all VPU instructions). By vectorizing your loop, you can lower the cost of an iteration from 8.50 to 4.00 cycles (2.13x speedup).

Details

All VPU instructions are used in scalar version (process only one data element in vector registers). Since your execution units are vector units, only a vectorized loop can use their full power.

Workaround

Try another compiler or update/tune your current one
Remove inter-iterations dependences from your loop and make it unit-stride:
- If your arrays have 2 or more dimensions, check whether elements are accessed contiguously and, otherwise, try to permute loops accordingly: C storage order is row-major: for(i) for(j) a[j][i] = b[j][i]; (slow, non stride 1) => for(i) for(j) a[i][j] = b[i][j]; (fast, stride 1)
- If your loop streams arrays of structures (AoS), try to use structures of arrays instead (SoA): for(i) a[i].x = b[i].x; (slow, non stride 1) => for(i) a.x[i] = b.x[i]; (fast, stride 1)

No data for this section

Matching between your loop (in the source code) and the binary loop

The binary loop does not contain any FP arithmetical operations. The binary loop is loading 64 bytes. The binary loop is storing 64 bytes.

General properties

nb instructions	68
loop length	272
nb stack references	0

Front-end

FIT IN UOP CACHE

front end

8.50 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15	P16
uops	8.50	8.50	4.58	4.58	4.50	4.50	4.42	4.42	8.00	8.00	0.00	0.00	5.33	5.33	5.33	0.00	0.00
cycles	8.50	8.50	4.58	4.58	4.50	4.50	4.42	4.42	8.00	8.00	0.00	0.00	5.33	5.33	5.33	0.00	0.00

Execution ports to units layout:

P0: BRU
P1: BRU
P2: ALU
P3: ALU
P4: ALU
P5: ALU
P6: ALU
P7: ALU
P8 (128 bits): VPU, FP store data, ALU, DIV/SQRT
P9 (128 bits): VPU, ALU, FP store data
P10 (128 bits): VPU, ALU, DIV/SQRT
P11 (128 bits): ALU, VPU
P12 (256 bits): store address, load
P13 (256 bits): store address, load
P14 (256 bits): load
P15 (64 bits): store data
P16 (64 bits): store data

Cycles executing div or sqrt instructions

Cycles summary

Front-end	8.50
Overall L1	8.50

Vectorization ratios

INT

all	0%
load	0%
store	0%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
other	0%

all	0%
load	NA (no load vectorizable/vectorized instructions)
store	NA (no store vectorizable/vectorized instructions)
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	0%

INT+FP

all	0%
load	0%
store	0%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	0%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each iteration of the binary loop takes 8.50 cycles. At this rate:

7% of peak load performance is reached (7.53 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
15% of peak store performance is reached (7.53 out of 48.00 bytes stored per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the loop is: 420398

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P12	P13	P14	Latency	Recip. throughput	Vectorization
LDR D6, [X16]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (50.0%)
FCMPE D6, D31	1	0	0	0	0	0	0	0	0	1	0	0	0	0	2	1	scal (50.0%)
B.GE 4203b4 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x254>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CMP W23, W13	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	0	1	0.33	scal (25.0%)
B.EQ 4203b4 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x254>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
STR D6, [X6, X4,UXTW #3]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	2	0.50	scal (50.0%)
ADD W4, W4, #1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
LDR D7, [X16, #8]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (50.0%)
ADD W30, W13, #1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	scal (25.0%)
ADD X0, X16, #8	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
FCMPE D7, D31	1	0	0	0	0	0	0	0	0	1	0	0	0	0	2	1	scal (50.0%)
B.GE 4203d8 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x278>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CMP W23, W30	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	0	1	0.33	scal (25.0%)
B.EQ 4203d8 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x278>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
STR D7, [X6, X4,UXTW #3]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	2	0.50	scal (50.0%)
ADD W4, W4, #1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
LDR D8, [X0, #8]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (50.0%)
ADD W1, W30, #1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	scal (25.0%)
FCMPE D8, D31	1	0	0	0	0	0	0	0	0	1	0	0	0	0	2	1	scal (50.0%)
B.GE 4203f8 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x298>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CMP W23, W1	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	0	1	0.33	scal (25.0%)
B.EQ 4203f8 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x298>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
STR D8, [X6, X4,UXTW #3]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	2	0.50	scal (50.0%)
ADD W4, W4, #1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
LDR D9, [X0, #16]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (50.0%)
ADD W2, W30, #2	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	scal (25.0%)
FCMPE D9, D31	1	0	0	0	0	0	0	0	0	1	0	0	0	0	2	1	scal (50.0%)
B.GE 420418 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x2b8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CMP W23, W2	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	0	1	0.33	scal (25.0%)
B.EQ 420418 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x2b8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
STR D9, [X6, X4,UXTW #3]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	2	0.50	scal (50.0%)
ADD W4, W4, #1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
LDR D10, [X0, #24]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (50.0%)
ADD W28, W30, #3	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	scal (25.0%)
FCMPE D10, D31	1	0	0	0	0	0	0	0	0	1	0	0	0	0	2	1	scal (50.0%)
B.GE 420438 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x2d8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CMP W23, W28	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	0	1	0.33	scal (25.0%)
B.EQ 420438 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x2d8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
STR D10, [X6, X4,UXTW #3]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	2	0.50	scal (50.0%)
ADD W4, W4, #1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
LDR D11, [X0, #32]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (50.0%)
ADD W3, W30, #4	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	scal (25.0%)
FCMPE D11, D31	1	0	0	0	0	0	0	0	0	1	0	0	0	0	2	1	scal (50.0%)
B.GE 420458 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x2f8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CMP W23, W3	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	0	1	0.33	scal (25.0%)
B.EQ 420458 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x2f8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
STR D11, [X6, X4,UXTW #3]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	2	0.50	scal (50.0%)
ADD W4, W4, #1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
LDR D12, [X0, #40]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (50.0%)
ADD W27, W30, #5	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	scal (25.0%)
FCMPE D12, D31	1	0	0	0	0	0	0	0	0	1	0	0	0	0	2	1	scal (50.0%)
B.GE 420478 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x318>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CMP W23, W27	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	0	1	0.33	scal (25.0%)
B.EQ 420478 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x318>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
STR D12, [X6, X4,UXTW #3]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	2	0.50	scal (50.0%)
ADD W4, W4, #1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
LDR D13, [X0, #48]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (50.0%)
ADD W12, W30, #6	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	scal (25.0%)
FCMPE D13, D31	1	0	0	0	0	0	0	0	0	1	0	0	0	0	2	1	scal (50.0%)
B.GE 420498 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x338>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CMP W23, W12	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	0	1	0.33	scal (25.0%)
B.EQ 420498 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x338>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
STR D13, [X6, X4,UXTW #3]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	2	0.50	scal (50.0%)
ADD W4, W4, #1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
ADD W13, W30, #7	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
ADD X16, X0, #56	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
CMP W5, W13	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	0	1	0.33	N/A
B.NE 420398 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x238>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A

Function	miniqmcreference::TwoBodyJastrowRef >::evaluateRatios(qmcplusplus::VirtualParticleSet&, std::vector >&)
Source file and lines	BsplineFunctor.h:236-241
Module	exec

Ignoring paths for analysis
Too many paths. If you really need to analyze all of the 6561 paths individually, rerun with max-paths=6561
RecMII not computed since number of paths is unknown or > max_paths
Streams not analyzed since number of paths is unknown or > max_paths

hoisting them (moving them outside the loop)
turning them into conditional moves, MIN or MAX

Ex: if (x<0) x=0 => x = (x<0 ? 0 : x) (or MAX(0,x) after defining the corresponding macro)

gain
potential
hint
expert

Code clean check

Detected a slowdown caused by scalar integer instructions (typically used for address computation). By removing them, you can lower the cost of an iteration from 8.50 to 5.33 cycles (1.59x speedup).

Workaround

Try to reorganize arrays of structures to structures of arrays
Consider to permute loops (see vectorization gain report)

Vectorization

Details

All VPU instructions are used in scalar version (process only one data element in vector registers). Since your execution units are vector units, only a vectorized loop can use their full power.

Workaround

Try another compiler or update/tune your current one
Remove inter-iterations dependences from your loop and make it unit-stride:
- If your arrays have 2 or more dimensions, check whether elements are accessed contiguously and, otherwise, try to permute loops accordingly: C storage order is row-major: for(i) for(j) a[j][i] = b[j][i]; (slow, non stride 1) => for(i) for(j) a[i][j] = b[i][j]; (fast, stride 1)
- If your loop streams arrays of structures (AoS), try to use structures of arrays instead (SoA): for(i) a[i].x = b[i].x; (slow, non stride 1) => for(i) a.x[i] = b.x[i]; (fast, stride 1)

No data for this section

Matching between your loop (in the source code) and the binary loop

The binary loop does not contain any FP arithmetical operations. The binary loop is loading 64 bytes. The binary loop is storing 64 bytes.

General properties

nb instructions	68
loop length	272
nb stack references	0

Front-end

FIT IN UOP CACHE

front end

8.50 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15	P16
uops	8.50	8.50	4.58	4.58	4.50	4.50	4.42	4.42	8.00	8.00	0.00	0.00	5.33	5.33	5.33	0.00	0.00
cycles	8.50	8.50	4.58	4.58	4.50	4.50	4.42	4.42	8.00	8.00	0.00	0.00	5.33	5.33	5.33	0.00	0.00

Execution ports to units layout:

P0: BRU
P1: BRU
P2: ALU
P3: ALU
P4: ALU
P5: ALU
P6: ALU
P7: ALU
P8 (128 bits): VPU, FP store data, ALU, DIV/SQRT
P9 (128 bits): VPU, ALU, FP store data
P10 (128 bits): VPU, ALU, DIV/SQRT
P11 (128 bits): ALU, VPU
P12 (256 bits): store address, load
P13 (256 bits): store address, load
P14 (256 bits): load
P15 (64 bits): store data
P16 (64 bits): store data

Cycles executing div or sqrt instructions

Cycles summary

Front-end	8.50
Overall L1	8.50

Vectorization ratios

INT

all	0%
load	0%
store	0%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
other	0%

all	0%
load	NA (no load vectorizable/vectorized instructions)
store	NA (no store vectorizable/vectorized instructions)
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	0%

INT+FP

all	0%
load	0%
store	0%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	0%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each iteration of the binary loop takes 8.50 cycles. At this rate:

7% of peak load performance is reached (7.53 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
15% of peak store performance is reached (7.53 out of 48.00 bytes stored per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the loop is: 420398

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P12	P13	P14	Latency	Recip. throughput	Vectorization
LDR D6, [X16]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (50.0%)
FCMPE D6, D31	1	0	0	0	0	0	0	0	0	1	0	0	0	0	2	1	scal (50.0%)
B.GE 4203b4 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x254>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CMP W23, W13	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	0	1	0.33	scal (25.0%)
B.EQ 4203b4 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x254>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
STR D6, [X6, X4,UXTW #3]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	2	0.50	scal (50.0%)
ADD W4, W4, #1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
LDR D7, [X16, #8]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (50.0%)
ADD W30, W13, #1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	scal (25.0%)
ADD X0, X16, #8	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
FCMPE D7, D31	1	0	0	0	0	0	0	0	0	1	0	0	0	0	2	1	scal (50.0%)
B.GE 4203d8 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x278>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CMP W23, W30	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	0	1	0.33	scal (25.0%)
B.EQ 4203d8 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x278>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
STR D7, [X6, X4,UXTW #3]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	2	0.50	scal (50.0%)
ADD W4, W4, #1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
LDR D8, [X0, #8]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (50.0%)
ADD W1, W30, #1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	scal (25.0%)
FCMPE D8, D31	1	0	0	0	0	0	0	0	0	1	0	0	0	0	2	1	scal (50.0%)
B.GE 4203f8 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x298>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CMP W23, W1	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	0	1	0.33	scal (25.0%)
B.EQ 4203f8 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x298>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
STR D8, [X6, X4,UXTW #3]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	2	0.50	scal (50.0%)
ADD W4, W4, #1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
LDR D9, [X0, #16]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (50.0%)
ADD W2, W30, #2	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	scal (25.0%)
FCMPE D9, D31	1	0	0	0	0	0	0	0	0	1	0	0	0	0	2	1	scal (50.0%)
B.GE 420418 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x2b8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CMP W23, W2	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	0	1	0.33	scal (25.0%)
B.EQ 420418 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x2b8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
STR D9, [X6, X4,UXTW #3]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	2	0.50	scal (50.0%)
ADD W4, W4, #1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
LDR D10, [X0, #24]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (50.0%)
ADD W28, W30, #3	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	scal (25.0%)
FCMPE D10, D31	1	0	0	0	0	0	0	0	0	1	0	0	0	0	2	1	scal (50.0%)
B.GE 420438 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x2d8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CMP W23, W28	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	0	1	0.33	scal (25.0%)
B.EQ 420438 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x2d8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
STR D10, [X6, X4,UXTW #3]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	2	0.50	scal (50.0%)
ADD W4, W4, #1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
LDR D11, [X0, #32]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (50.0%)
ADD W3, W30, #4	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	scal (25.0%)
FCMPE D11, D31	1	0	0	0	0	0	0	0	0	1	0	0	0	0	2	1	scal (50.0%)
B.GE 420458 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x2f8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CMP W23, W3	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	0	1	0.33	scal (25.0%)
B.EQ 420458 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x2f8>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
STR D11, [X6, X4,UXTW #3]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	2	0.50	scal (50.0%)
ADD W4, W4, #1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
LDR D12, [X0, #40]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (50.0%)
ADD W27, W30, #5	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	scal (25.0%)
FCMPE D12, D31	1	0	0	0	0	0	0	0	0	1	0	0	0	0	2	1	scal (50.0%)
B.GE 420478 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x318>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CMP W23, W27	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	0	1	0.33	scal (25.0%)
B.EQ 420478 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x318>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
STR D12, [X6, X4,UXTW #3]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	2	0.50	scal (50.0%)
ADD W4, W4, #1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
LDR D13, [X0, #48]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	6	0.33	scal (50.0%)
ADD W12, W30, #6	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	scal (25.0%)
FCMPE D13, D31	1	0	0	0	0	0	0	0	0	1	0	0	0	0	2	1	scal (50.0%)
B.GE 420498 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x338>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CMP W23, W12	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	0	1	0.33	scal (25.0%)
B.EQ 420498 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x338>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
STR D13, [X6, X4,UXTW #3]	1	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	0	2	0.50	scal (50.0%)
ADD W4, W4, #1	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
ADD W13, W30, #7	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
ADD X16, X0, #56	1	0	0	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	1	0.17	N/A
CMP W5, W13	1	0	0	0.25	0.25	0	0	0.25	0.25	0	0	0	0	0	1	0.33	N/A
B.NE 420398 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x238>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A

Report Configuration

Code clean check

Workaround

Vectorization

Details

Workaround

Matching between your loop (in the source code) and the binary loop

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Cycles and memory resources usage

ASM code

Code clean check

Workaround

Vectorization

Details

Workaround

Matching between your loop (in the source code) and the binary loop

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Cycles and memory resources usage

ASM code